List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL hopper-medium v2 (test)

99.4Normalized RewardDDT
28.36846.80965.2583.691Jan 22, 2026
Updated 8mo ago

Evaluation results

MethodLinks
DDT2026.0199.4
VDT2026.0198.3
LSDT2026.0187.2
DT2026.0168.3
IQL2026.0166.3
TD3+BC2026.0159.3
CQL2026.0158
BRAC-v2026.0131.1